ePrints.FRI - University of Ljubljana, Faculty of Computer and Information Science

Machine Learning Approaches for analysis of League of Legends

Simon Janežič (2016) Machine Learning Approaches for analysis of League of Legends. EngD thesis.

Download (4Mb)


    Our goal is to use machine learning for predicting winners of League of Legends matches. League of Legends is a multiplayer game that combines elements from strategic and action games. Every year, multiple professional League of Legends competitions are being held acros the globe. We try to predict both professional and non-professional matches. Getting data for both types of matches is already a challenge. For non-professional matches official application programming interface is used, while data for professional matches is gathered using web scraping. We begin our research by using the collected data for initial analysis, where we compare player statistics from different ranks. We find some interesting differences that lower-ranked players could use to improve their game without huge amount of effort. After that, we use standard machine learning approaches to predict match winners. Classificators for non-professional matches yield similar results to a recently published study. We also compare the results for both types of matches and find that it is easier to predict the outcomes of professional matches.

    Item Type: Thesis (EngD thesis)
    Keywords: machine learning, data mining, League of Legends, game outcome prediction
    Number of Pages: 50
    Language of Content: Slovenian
    Mentor / Comentors:
    Name and SurnameIDFunction
    prof. dr. Blaž Zupan106Mentor
    Link to COBISS: http://www.cobiss.si/scripts/cobiss?command=search&base=51012&select=(ID=1537070787 )
    Institution: University of Ljubljana
    Department: Faculty of Computer and Information Science
    Item ID: 3427
    Date Deposited: 18 Aug 2016 15:04
    Last Modified: 30 Aug 2016 10:15
    URI: http://eprints.fri.uni-lj.si/id/eprint/3427

    Actions (login required)

    View Item